(006)Hadoop基础之job的文件split计算法则

 public List getSplits(JobContext job) throws IOException {
        Stopwatch sw = (new Stopwatch()).start();
        long minSize = Math.max(this.getFormatMinSplitSize(), getMinSplitSize(job));
        long maxSize = getMaxSplitSize(job);
        List splits = new ArrayList();
        List files = this.listStatus(job);
        Iterator i$ = files.iterator();
        while(true) {
            while(true) {
                while(i$.hasNext()) {
                    FileStatus file = (FileStatus)i$.next();
                    Path path = file.getPath();
                    long length = file.getLen();
                    if (length != 0L) {
                        BlockLocation[] blkLocations;
                        if (file instanceof LocatedFileStatus) {
                            blkLocations = ((LocatedFileStatus)file).getBlockLocations();
                        } else {
                            FileSystem fs = path.getFileSystem(job.getConfiguration());
                            blkLocations = fs.getFileBlockLocations(file, 0L, length);
                        }
                        if (this.isSplitable(job, path)) {
                            long blockSize = file.getBlockSize();
                            long splitSize = this.computeSplitSize(blockSize, minSize, maxSize);

                            long bytesRemaining;
                            int blkIndex;
                            for(bytesRemaining = length; (double)bytesRemaining / (double)splitSize > 1.1D; bytesRemaining -= splitSize) {
                                blkIndex = this.getBlockIndex(blkLocations, length - bytesRemaining);
                                splits.add(this.makeSplit(path, length - bytesRemaining, splitSize, blkLocations[blkIndex].getHosts(), blkLocations[blkIndex].getCachedHosts()));
                            }
                            if (bytesRemaining != 0L) {
                                blkIndex = this.getBlockIndex(blkLocations, length - bytesRemaining);
                                splits.add(this.makeSplit(path, length - bytesRemaining, bytesRemaining, blkLocations[blkIndex].getHosts(), blkLocations[blkIndex].getCachedHosts()));
                            }
                        } else {
                            splits.add(this.makeSplit(path, 0L, length, blkLocations[0].getHosts(), blkLocations[0].getCachedHosts()));
                        }
                    } else {
                        splits.add(this.makeSplit(path, 0L, length, new String[0]));
                    }
                }
                job.getConfiguration().setLong("mapreduce.input.fileinputformat.numinputfiles", (long)files.size());
                sw.stop();
                if (LOG.isDebugEnabled()) {
                    LOG.debug("Total # of splits generated by getSplits: " + splits.size() + ", TimeTaken: " + sw.elapsedMillis());
                }
                return splits;
            }
        }
    }